GB2597406A - Fairness improvement through reinforcement learning - Google Patents
Fairness improvement through reinforcement learning Download PDFInfo
- Publication number
- GB2597406A GB2597406A GB2115858.9A GB202115858A GB2597406A GB 2597406 A GB2597406 A GB 2597406A GB 202115858 A GB202115858 A GB 202115858A GB 2597406 A GB2597406 A GB 2597406A
- Authority
- GB
- United Kingdom
- Prior art keywords
- mlm
- fairness
- original
- provisional
- program instructions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Abstract
A computer-implemented method for improving fairness in a supervised machine-learning model may be provided. The method comprises linking the supervised machine-learning model to a reinforcement learning meta model, selecting a list of hyper-parameters and parameters of the supervised machine-learning model, and controlling at least one aspect of the supervised machine-learning model by adjusting hyper-parameters values and parameter values of the list of hyper-parameters and parameters of the supervised machine-learning model by a reinforcement learning engine relating to the reinforcement learning meta model by calculating a reward function based on multiple conflicting objective functions. The method further comprises repeating iteratively the steps of selecting and controlling for improving a fairness value of the supervised machine-learning model.
Claims (20)
1. A computer-implemented method, the method comprising: receiving an original version of a machine learning model (MLM) including a plurality of parameter values, a plurality of hyperparameter values and an original fairness value that reflects fairness with respect to segmented relevant sub-groups; adjusting at least some of the parameter values and/or at least some of the hyperparameter values of the original version of the MLM to create a provisional version of the MLM; determining a fairness value for the provisional version of the MLM by operations including the following: receiving a reinforcement learning meta model (RLMM) that defines a plurality of fairness related objectives and a reward function reflecting the plurality of fairness related objectives; operating the provisional version of the MLM; during the operation of the provisional version of the MLM, calculating, by the RLMM, reward values based on the reward function; and determining a provisional fairness value for the provisional version of the MLM based upon the reward values; determining that the provisional fairness value is greater than the original fairness value; and responsive to the determination that the provisional fairness value is greater than the original fairness value, replacing the original version of the MLM with the provisional version of the MLM and replacing the original fairness value with the provisional fairness value.
2. The computer-implemented method of claim 1, further comprising: iteratively repeating the operations of until the original fairness value exceeds a predetermined threshold.
3. The computer-implemented method of claim 1 or 2, wherein the original MLM is a supervised MLM.
4. The computer-implemented method of one of claims 1 to 3, wherein the fairness related objectives include at least one of the following: gender, age, nationality, religious beliefs, ethnicity and orientation.
5. The computer-implemented method of one of claims 1 to 4, further comprising: linking the original MLM to the reinforcement learning meta model based on a configuration and a read out.
6. The computer-implemented method of one of claims 1 to 5, wherein the plurality of parameter values includes a value for at least one of the following parameter types: weighing factors and activation function variables.
7. The computer-implemented method of claim 1 to 6, wherein the plurality of hyperparameter values include a value for at least one of the following hyperparameter types: type of activation function, number of nodes per layer, number of layers of a neural network and machine-learning model.
8. A computer program product, the computer program product comprising: one or more non-transitory computer readable storage media and program instructions stored on the one or more non-transitory computer readable storage media, the program instructions comprising: program instructions to receive an original version of a machine learning model (MLM) including a plurality of parameter values, a plurality of hyperparameter values and an original fairness value that reflects fairness with respect to segmented relevant sub-groups; program instructions to adjust at least some of the parameter values and/or at least some of the hyperparameter values of the original version of the MLM to create a provisional version of the MLM; program instructions to determine a fairness value for the provisional version of the MLM by operations including the following: program instructions to receive a reinforcement learning meta model (RLMM) that defines a plurality of fairness related objectives and a reward function reflecting the plurality of fairness related objectives; program instructions to operate the provisional version of the MLM; during the operation of the provisional version of the MLM, program instructions to calculate, by the RLMM, reward values based on the reward function; and program instructions to determine a provisional fairness value for the provisional version of the MLM based upon the reward values; program instructions to determine that the provisional fairness value is greater than the original fairness value; and responsive to the determination that the provisional fairness value is greater than the original fairness value, program instructions to replace the original version of the MLM with the provisional version of the MLM and replacing the original fairness value with the provisional fairness value.
9. The computer program product of claim 8, further comprising: program instructions to iteratively repeating the operations of until the original fairness value exceeds a predetermined threshold.
10. The computer program product of claim 8 or 9, wherein the original MLM is a supervised MLM.
11. The computer program product of one of claims 8 to 10, wherein the fairness related objectives include at least one of the following: gender, age, nationality, religious beliefs, ethnicity and orientation.
12. The computer program product of one of claims 8 to 11, further comprising: program instructions to link the original MLM to the reinforcement learning meta model based on a configuration and a read out.
13. The computer program product of one of claims 8 to 12, wherein the plurality of parameter values includes a value for at least one of the following parameter types: weighing factors and activation function variables.
14. The computer program product of one of claim 8 to 13, wherein the plurality of hyperparameter values include a value for at least one of the following hyperparameter types: type of activation function, number of nodes per layer, number of layers of a neural network and machine-learning model.
15. A computer system, comprising: one or more computer processors; one or more computer readable storage media; program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising: program instructions to receive an original version of a machine learning model (MLM) including a plurality of parameter values, a plurality of hyperparameter values and an original fairness value that reflects fairness with respect to segmented relevant sub-groups; program instructions to adjust at least some of the parameter values and/or at least some of the hyperparameter values of the original version of the MLM to create a provisional version of the MLM; program instructions to determine a fairness value for the provisional version of the MLM by operations including the following: program instructions to receive a reinforcement learning meta model (RLMM) that defines a plurality of fairness related objectives and a reward function reflecting the plurality of fairness related objectives; program instructions to operate the provisional version of the MLM; during the operation of the provisional version of the MLM, program instructions to calculate, by the RLMM, reward values based on the reward function; and program instructions to determine a provisional fairness value for the provisional version of the MLM based upon the reward values; program instructions to determine that the provisional fairness value is greater than the original fairness value; and responsive to the determination that the provisional fairness value is greater than the original fairness value, program instructions to replace the original version of the MLM with the provisional version of the MLM and replacing the original fairness value with the provisional fairness value.
16. The computer system of claim 15, further comprising: program instructions to iteratively repeating the operations of until the original fairness value exceeds a predetermined threshold.
17. The computer system of claim 15 or 16, wherein the fairness related objectives include at least one of the following: gender, age, nationality, religious beliefs, ethnicity and orientation.
18. The computer system of one of claims 15 to 17, further comprising: program instructions to link the original MLM to the reinforcement learning meta model based on a configuration and a read out.
19. The computer system of one of claims 15 to 18, wherein the plurality of parameter values includes a value for at least one of the following parameter types: weighing factors and activation function variables.
20. The computer system of one of claims 15 to 19, wherein the plurality of hyperparameter values include a value for at least one of the following hyperparameter types: type of activation function, number of nodes per layer, number of layers of a neural network and machine-learning model.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/377,727 US20200320428A1 (en) | 2019-04-08 | 2019-04-08 | Fairness improvement through reinforcement learning |
| PCT/IB2020/052465 WO2020208444A1 (en) | 2019-04-08 | 2020-03-18 | Fairness improvement through reinforcement learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| GB2597406A true GB2597406A (en) | 2022-01-26 |
Family
ID=72663093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB2115858.9A Withdrawn GB2597406A (en) | 2019-04-08 | 2020-03-18 | Fairness improvement through reinforcement learning |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US20200320428A1 (en) |
| JP (1) | JP2022527536A (en) |
| CN (1) | CN113692594A (en) |
| DE (1) | DE112020000537T5 (en) |
| GB (1) | GB2597406A (en) |
| WO (1) | WO2020208444A1 (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11636386B2 (en) * | 2019-11-21 | 2023-04-25 | International Business Machines Corporation | Determining data representative of bias within a model |
| US11556826B2 (en) * | 2020-03-20 | 2023-01-17 | Adobe Inc. | Generating hyper-parameters for machine learning models using modified Bayesian optimization based on accuracy and training efficiency |
| US11551178B2 (en) * | 2020-05-14 | 2023-01-10 | Wells Fargo Bank, N.A. | Apparatuses and methods for regulation offending model prevention |
| US20210383268A1 (en) * | 2020-06-03 | 2021-12-09 | Discover Financial Services | System and method for mitigating bias in classification scores generated by machine learning models |
| CN112163677B (en) * | 2020-10-14 | 2023-09-19 | 杭州海康威视数字技术股份有限公司 | Method, device and equipment for applying machine learning model |
| CN112257848B (en) * | 2020-10-22 | 2024-04-30 | 北京灵汐科技有限公司 | Method for determining logic core layout, model training method, electronic device and medium |
| WO2022115402A1 (en) * | 2020-11-27 | 2022-06-02 | Amazon Technologies, Inc. | Staged bias measurements in machine learning pipelines |
| CN112416602B (en) * | 2020-12-10 | 2022-09-16 | 清华大学 | Distributed data stream resource elastic expansion enhancing plug-in and enhancing method |
| CN112905465B (en) * | 2021-02-09 | 2022-07-22 | 中国科学院软件研究所 | Machine learning model black box fairness test method and system based on deep reinforcement learning |
| US20220391683A1 (en) * | 2021-06-07 | 2022-12-08 | International Business Machines Corporation | Bias reduction during artifical intelligence module training |
| EP4106231A1 (en) * | 2021-06-14 | 2022-12-21 | Google LLC | Selection of physics-specific model for determination of characteristics of radio frequency signal propagation |
| US20230351172A1 (en) * | 2022-04-29 | 2023-11-02 | Intuit Inc. | Supervised machine learning method for matching unsupervised data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242105A (en) * | 2018-08-17 | 2019-01-18 | 第四范式（北京）技术有限公司 | Tuning method, apparatus, equipment and the medium of hyper parameter in machine learning model |
| US20190095818A1 (en) * | 2017-09-28 | 2019-03-28 | Oracle International Corporation | Gradient-based auto-tuning for machine learning and deep learning models |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9008840B1 (en) | 2013-04-19 | 2015-04-14 | Brain Corporation | Apparatus and methods for reinforcement-guided supervised learning |
| US10839302B2 (en) | 2015-11-24 | 2020-11-17 | The Research Foundation For The State University Of New York | Approximate value iteration with complex returns by bounding |
-
2019
- 2019-04-08 US US16/377,727 patent/US20200320428A1/en not_active Abandoned
-
2020
- 2020-03-18 DE DE112020000537.2T patent/DE112020000537T5/en active Pending
- 2020-03-18 GB GB2115858.9A patent/GB2597406A/en not_active Withdrawn
- 2020-03-18 WO PCT/IB2020/052465 patent/WO2020208444A1/en active Application Filing
- 2020-03-18 JP JP2021558964A patent/JP2022527536A/en active Pending
- 2020-03-18 CN CN202080027018.4A patent/CN113692594A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190095818A1 (en) * | 2017-09-28 | 2019-03-28 | Oracle International Corporation | Gradient-based auto-tuning for machine learning and deep learning models |
| CN109242105A (en) * | 2018-08-17 | 2019-01-18 | 第四范式（北京）技术有限公司 | Tuning method, apparatus, equipment and the medium of hyper parameter in machine learning model |
Non-Patent Citations (2)
| Title |
|---|
| Sam Corbett-Davies et al. "The Measure and Mismeasure of Fairness:A Critical Review of Fair Machine Learning", http://arxiv.org/abs/1808.00023, 14 August 2018, the whole document * |
| Sorelle A. Friedler et al. "A comparative study of fairness-enhancing interventions in machine learning", Proceedings of the Conference on Fairness, Accountability, and Transparency, 19 January 2019, Pages 329-338, https://doi.org/10.1145/3287560.3287589, the whole document * |
Also Published As
| Publication number | Publication date |
|---|---|
| DE112020000537T5 (en) | 2021-10-21 |
| US20200320428A1 (en) | 2020-10-08 |
| CN113692594A (en) | 2021-11-23 |
| JP2022527536A (en) | 2022-06-02 |
| WO2020208444A1 (en) | 2020-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2597406A (en) | Fairness improvement through reinforcement learning | |
| US11893466B2 (en) | Systems and methods for model fairness | |
| US11734066B2 (en) | Resource scheduling using machine learning | |
| US11087245B2 (en) | Predictive issue detection | |
| EP3475798A1 (en) | Data quality detection and compensation for machine learning | |
| CN111125864A (en) | Asset performance manager associated with the availability and use of used available materials | |
| US10324705B2 (en) | System and method for run-time update of predictive analytics system | |
| US11468379B2 (en) | Automated evaluation of project acceleration | |
| US20210241292A1 (en) | System and method for profiling and predicting customer behavior | |
| KR20210030182A (en) | Method and apparatus for monitoring vacancy rate of warehouse using artificial intelligence model | |
| JP7191058B2 (en) | Tunable bias reduction pipeline | |
| Ramesh | Predictive analytics for banking user data using AWS machine learning cloud service | |
| US11914342B2 (en) | Autozoning of additive manufacturing print parameters | |
| GB2593604A (en) | Prediction model enhancement | |
| JP2019087101A (en) | Anticipation model maintenance system, method for maintaining anticipation model, and anticipation model maintenance program | |
| KR20220111179A (en) | Techniques for determining a store demand forecasting model | |
| WO2022251162A1 (en) | Resource allocation optimization for multi-dimensional machine learning environments | |
| JPWO2020208444A5 (en) | ||
| US20220129789A1 (en) | Code generation for deployment of a machine learning model | |
| US11538047B2 (en) | Utilizing a machine learning model to determine attribution for communication channels | |
| US20170160730A1 (en) | Production system having constraint evaluator generating constrained sequences | |
| Riesener et al. | Implementing Neural Networks within Portfolio Management to Support Decision-Making Processes | |
| US20210031302A1 (en) | Assignment of multiple print parameter sets in additive manufacturing | |
| EP4305565A1 (en) | Computer-implemented methods referring to an industrial process for manufacturing a product and system for performing said methods | |
| CN108897818B (en) | Method and device for determining aging state of data processing process and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WAP | Application withdrawn, taken to be withdrawn or refused ** after publication under section 16(1) |